Getting it right the second time: Recognition of spoken corrections

We investigate ways to improve recognition accuracy on spoken corrections. We show that a variety of simple techniques can greatly improve the accuracy on corrections. We further develop a flexible merge model that improves accuracy by combining information from the original recognition and the spoken correction. Our merge model operates on word confusion networks and can easily incorporate prior beliefs about the recognition events (e.g. which words are likely correct or incorrect). By combining all of our techniques, the percentage of correctly recognized spoken corrections increased from 21% to 53%.